Earticle

The importance of recommendation algorithms is underscored by the advancement of AI technology and the growing demand for personalized services. However, there is a lack of empirical studies that analyze differences in algorithmic services across markets. The objective of this study is to draw attention to discrepancy in this field and develop a dual-path model to examine the factors that influence satisfaction with recommendations. By analyzing 641 respondents’ data through Partial Least Squares (PLS), it identifies differences in user attitudes towards algorithms across domains. e-commerce firms and content providers can improve personalized recommendations through the research, which highlights the importance of understanding consumer satisfaction and trust in technology to adapt to evolving AI innovations.

해양 분야에서는 인력 부족과 인건비 증가 등의 문제를 해결하기 위하여 무인 운영 체제에 대한 다양한 연구가 진행 중이 다. 해군에서도 인력 감소 대처와 승무원의 안전 보장을 위해 무인 체계에 대한 관심을 보이고 있다. 본 논문은 무인 함정 체계의 자율운항 기술 중 핵심 기술인 충돌 회피 알고리즘 개발을 목적으로 한다. 충돌 회피 알고리즘은 운항 시 조우할 수 있는 정적 장애물과 동적 장애물을 모두 회피할 수 있어야 하며, 센서의 사용이 제한되는 상황에서도 장애물을 회피할 수 있 어야 한다. 이러한 알고리즘을 개발하기 위해 함정의 ACDIS 추출 데이터와 AIS 데이터를 이용하며, Vector Field Histogram(VFH)과 Velocity Obstacle method(VO)를 융합하여 충돌 회피 알고리즘을 개발하였다. 이를 검증하기 위해 MMG 수학모델을 이용한 시뮬레이션 환경을 구축하였으며, 제시한 알고리즘을 이용할 경우 정적 장애물, 동적 장애물, 두 가 지 장애물을 동시에 조우하는 상황에서도 충돌 회피가 가능함을 시뮬레이션을 통해 확인하였다.

In the maritime industry, various research is underway to address issues such as labor shortages and increasing labor costs by developing unmanned operating systems. The Navy is also showing interest in unmanned systems to cope with manpower reduction and ensure the safety of crew members. This paper aims to develop collision avoidance algorithms, a key technology in autonomous navigation systems for unmanned surface vehicles. The collision avoidance algorithm should be able to avoid both static and dynamic obstacles that may be encountered during navigation, even in situations where sensor use is limited. To develop such an algorithm, ACDIS extraction data and AIS data were utilized, and a collision avoidance algorithm was developed by integrating the Vector Field Histogram (VFH) and Velocity Obstacle method (VO). To validate the proposed algorithm, a simulation environment was created using the MMG mathematical model, and through simulations, it was confirmed that collision avoidance is possible even in situations where static obstacles, dynamic obstacles, and both types of obstacles are encountered simultaneously.

This paper presents efficient guidelines that allow unmanned ground vehicles (UGVs) to avoid obstacles and interpret sensor data, which were executed by an embedded real-time processor for rapid control prototyping (RCP) model using a graphic system design (GSD) programming language. The obstacle avoidance algorithm uses data from laser sensors in order to enable the UGV to make decisions on how to navigate around its environment. Our research control algorithm was implemented on a real-time system, and data were transferred from a real-time processor to a robot. The robot successfully moved towards its goal by pre-making way-points and avoiding arbitrary obstacles by following the newly made way-points using this algorithm. By integrating commercially-available, off-the-shelf hardware and by using GSD program, we greatly improved the repeatability of developing an autonomous robot that drives and plans its own path.

자율주행 차량은 레이더, 라이다 카메라 등 다양한 로컬 센서들을 활용하여 주변 환경을 인지하고 판단하여 주행한다. 하지만 로컬 센서만을 활용하여 주행할 경우 인지 범위 한계로 장애물에 가려진 보행자나 자전거와 같은 VRU(Vulnerable Road User, 취약 도로 사용자)의 거 동 정보를 예측하기 어렵다. 본 논문에서는 이러한 로컬 센서의 한계를 극복하기 위해 V2X 통신 정보를 활용한 VRU 충돌 회피 알고리즘을 개발하였다. 알고리즘은 인프라로부터 충돌 위험이 있는 VRU의 정보를 전달 받아 미래 거동을 예측하고 주변 환경에 따라 적절하게 조향 및 제동 회피를 수행하도록 설계하였다. 개발된 알고리즘을 검증하기 위하여 다양한 조건의 시나리오에서 시뮬레이션을 수행하였으며, 그 결과, 기존 로컬 센서 정보만을 활용하였을 때 보다 개선된 충돌 회피 성능을 보일 뿐만 아니라, 차량의 안정성 또한 확보할 수 있음을 확인 하였다.

Autonomous vehicles use various local sensors such as camera, radar, and lidar to perceive the surrounding environment. However, it is difficult to predict the movement of vulnerable road users using only local sensors that are subject to limits in cognitive range. This is true especially when these users are blocked from view by obstacles. Hence, this paper developed an algorithm for collision avoidance with VRU using V2X information. The main purpose of this collision avoidance system is to overcome the limitations of the local sensors. The algorithm first evaluates the risk of collision, based on the current driving condition and the V2X information of the VRU. Subsequently, the algorithm takes one of four evasive actions; steering, braking, steering after braking, and braking after steering. A simulation was performed under various conditions. The results of the simulation confirmed that the algorithm could significantly improve the performance of the collision avoidance system while securing vehicle stability during evasive maneuvers.

지상 무인 차량(UGV), 무인기(UAV), 무인수상정(USV), 무인잠수정(UUV), 로봇 등과 같은 다중 무인체가 대형을 이루면서 군집 주행을 할 때 충돌회피 문제는 다중 에이전트 시스템에서 기본적으로 구현해야 하는 것으로 중요하게 인식되었다. 다중무 인체들은 가까운 미래에 생화학 오염지역이나 위험한 전투지역에서의 신속하게 투입되어 주어진 임무를 수행할 것이다. 다중 무인체가 편대를 이루어 출발지점에서 목표점인 임무 지역으로 이동할 때 자율주행을 할 수 있는 선도-추종 대형제 어를 적용하고, 다중무인체가 군집 자율주행할 때 갑자기 동적장애물 등이 나타나거나 주행 경로상에 고정장애물이 존재할 경우 이를 회피하기 위해 인공전위장을 이용한다. 지상전에서 다중 무인체의 장애물 회피 시스템에 대한 대형제어 알고리즘 성능을 평가하기 위해, 다중 무인체가 각각 3대, 5대, 7대, 그리고 장애물이 각각 0개, 1개, 3개, 5개인 경우에 대해 이들을 조합한 여러 가지 군집 자율주행상황을 시뮬레이션하였다.

It has been importantly recognized that the collision avoidance problem of multiple unmanned vehicles(MUVs) such as UGV, UAV, USV, UUV, Robot, etc. for platoon autonomous navigation in dynamic environments should be implemented basically in multiple agent systems. In the near future, they will be dispatched quickly and carry out their assigned tasks in biochemical contaminated area or dangerous combant areas. When multiple unmanned vehicles form a platoon formation and move from the starting point to the target point, leader-follower formation control that can autonomously navigate is applied. When multiple unmanned vehicles are autonomously driving in clusters, if a dynamic obstacle suddenly appears or there is a fixed obstacle on the driving path, artificial potential is used to avoid them. In order to check the performance of the formation control algorithm for the obstacle avoidance system of multiple unmanned vehicles in ground warfare, in the case of multiple unmanned vehicles with 3, 5, 7, and 0, 1, 3, and 5 obstacles, respectively, various platooning autonomous navigation situations were simulated by combining them.

본 숏폼 광고의 AI 추천 알고리즘 특성이 광고 피로도와 광고 회피에 미치는 영향을 실증적 으로 분석하였다. 디지털 미디어 환경에서 급성장하고 있는 숏폼 콘텐츠 플랫폼은 AI 기 반 추천 알고리즘을 통해 개인화된 광고를 제공하고 있으나, 이러한 개인화가 오히려 광고 피로 도와 회피 행동을 유발할 수 있다는 문제의식에서 출발하였다. 본 연구는 확증편향, 지각된 침입 성, 지각된 최적화, AI 알고리즘 신뢰성을 주요 독립변인으로 설정하고, 광고 피로도를 매개변인 으로 하여 광고 회피에 미치는 영향을 검증하였다. 분석 결과, 지각된 침입성은 광고 피로도에 강한 정적 영향을, 확증편향과 AI 알고리즘 신뢰성은 광고 피로도에 부적 영향을 미치는 것으로 나타났다. 지각된 최적화는 광고 피로도에는 유의한 영향을 미치지 않았으나 광고 회피에는 직 접적인 부적 영향을 미쳤다. 광고 피로도는 광고 회피에 강한 정적 영향을 미쳤으며, 매개효과 분석 결과 지각된 침입성과 AI 알고리즘 신뢰성이 광고 피로도를 매개로 광고 회피에 유의한 영 향을 미치는 것을 확인하였다. 본 연구는 숏폼 광고 환경에서 AI 추천 알고리즘의 부정적 효과 메커니즘을 체계적으로 규명한 첫 연구으로 디지털 마케팅 이론 확장에 기여하며, 실무적으로는 광고 피로도와 회피를 완화하기 위한 알고리즘 최적화 전략을 제시한다.

This study empirically analyzes the impact of AI recommendation algorithm characteristics on ad fatigue and ad avoidance in short-form advertising. While short-form content platforms experiencing rapid growth in the digital media environment provide personalized advertisements through AI-based recommendation algorithms, this research originated from the recognition that such personalization may paradoxically induce ad fatigue and avoidance behaviors. The study established confirmation bias, perceived intrusiveness, perceived optimization, and AI algorithm trustworthiness as major independent variables, with ad fatigue as a mediating variable to examine their effects on ad avoidance. The results revealed that perceived intrusiveness had a strong positive effect on ad fatigue, while confirmation bias and AI algorithm trustworthiness had negative effects on ad fatigue. Perceived optimization did not significantly affect ad fatigue but had a direct negative effect on ad avoidance. Ad fatigue had a strong positive effect on ad avoidance. The mediation analysis confirmed that perceived intrusiveness and AI algorithm trustworthiness significantly influenced ad avoidance through ad fatigue as a mediator. This study represents the first systematic investigation of the negative effect mechanisms of AI recommendation algorithms in short-form advertising environments, contributing to the expansion of digital marketing theory. Practically, it provides algorithm optimization strategies to mitigate ad fatigue and avoidance.

In this paper, we proposed the intersection collision avoidance (ICA) algorithm for bicycle to vehicle (B2V) safety service and analyzed its performance by using ‘PreScan’ and ‘MATLAB’. As typical type accidents related with bicycles, we consider the bicycle to vehicle (B2V) communication. The derived analytical approach can explain the condition and effect of bicycle collisions. Furthermore, proposed algorithm has been confirmed by simulations. Consequently, the ICA developing methodology is verified to be used as a general tool to reduce the cost and the time consumption required for commercialization of safety services under IEEE 802.11p/wireless access in vehicular environments (WAVE) wireless networks.

As ubiquitous computing technology convergences into many industrial domains, most museums want to apply this technique to their domain. However, most ubiquitous museums merely provide the simplest service giving visitors only static information of artifact. To resolve limitations of the existing ubiquitous museums, we had proposed Visitor Preference based Museum Viewing Search Algorithm that provides the best path for visitors to reflect their preferences. However, since the Visitor Preference based Museum Viewing Search Algorithm did not consider abnormal situations that occur while visitors look at the exhibit. So when abnormal situations occur, the exhibition may cause congestion problems that may make visitors feel very uncomfortable. In this paper, we propose an efficient congestion avoidance algorithm to solve these problems. This algorithm automatically re-finds proper alternative paths for avoiding congestion resulting from the abnormal ones occurring during the museum viewing. The proposed algorithm improves comfortable museum viewing services by preventing congestion in advance when exceptional conditions occur. For the experiment of the proposed algorithm, we show that the algorithm can provide the best path to reduce the impact of museum sightseeing crowdedness well even in exceptional conditions.

주어진 숫자 쌍 간에 빈 셀을 경유하는 선을 연결함에 있어 다른 숫자의 연결선과 교차가 발생하지 않도록 하는 숫자 연결 퍼즐은 다항시간으로 퍼즐을 풀 수 있는 방법이 알려져 있지 않은 NP-완전 문제이다. 지금까지는 임의의 숫자를 선정하여 시행착오 법으로 퍼즐을 풀고 있다. 본 논문은 주어진 문제에 대해 빈 셀을 정점으로, 인접 셀들 간에 간선으로 연결한 격자 그래프로 변환하였다. 다음으로 숫자 쌍 들 간에 직선을 긋고, 교차가 발생한 숫자 그룹으로 분할 하였다. 교차 숫자 그룹에서 교차를 회피하는 우회 경로를 설정하였다. 제안된 알고리즘을 18개의 벤치마킹 데이터들에 적용한 결과 모든 데이터에 대해 퍼즐을  의 선형시간 복잡도로 풀 수 있음을 보였다.

The numberlink puzzle(NLP), which non-crossings with other numbers of connection in connecting lines through empty cells between a given pair of numbers, is an NP-complete problem with no known way to solve the puzzle in polynomial time. Until now, arbitrary numbers have been selected and puzzles have been solved using trial-and-error methods. This paper converts empty cells into vertices in lattice graphs connected by edge between adjacent cells for a given problem. Next, a straight line was drawn between the pairs of numbers and divided into groups of numbers where crossing occurred. A bypass route was established to avoid intersection in the cross-number group. Applying the proposed algorithm to 18 benchmarking data showed that the puzzle could be solved with a linear time complexity of   for all data.

A collision-free formation reconfiguration trajectory subject to the linearized Hill's dynamics of relative motion is analytically developed by extending an algorithm for gravity-free space. Based on the initial solution without collision avoidance constraints, the final solution to minimize the designated performance index and avoid collision is found, based on a gradient method. Simple simulations confirm that satellites reconfigure their positions along the safe trajectories, while trying to spend minimum energies. The algorithm is applicable to wide range of formation flying under the Hill's dynamics.

In this paper, an obstacle avoidance algorithm is proposed for a network-based robot considering network delay by distribution. The proposed algorithm is based on the VFH(Vector Field Histogram) algorithm, and for the network-based robot system, in which it is assumed robot localization information is transmitted through network communication. In this paper, target vector for the VFH algorithm is estimated through the robot localization information and the measurement of its delay by distribution. The delay measurement is performed by time-stamp method. To synchronize all local clocks of the nodes distributed on the network, a global clock synchronization method is adopted. With the delay measurement, the robot localization estimation is performed by calculating the kinematics of the robot. The validation of the proposed algorithm is performed through the performance comparison of the obstacle avoidance between the proposed algorithm and the existing VFH algorithm on the network-based autonomous mobile robot.

Fruit harvesting robots should have more diversity and flexibility in the working conditions and environments than industrial robots. This paper presents an efficient optimization algorithm for redundant manipulators to avoid obstacles using dynamic performance criteria, while the optimization schemes of the previous studies used the performance criteria using kinematic approach. Feasibility and effectiveness of this algorithm were tested through simulations on a 3-degrees-of-freedom manipulator made for this study. Only the position of the end-effector was controlled , which requires only three degrees of freedom. Remaining joints, except for the wrist roll joint, which does not contribute to the end-effector linear velocity, provide two degrees of redundancy. The algorithm was effective to avoid obstacles in the workspace even through the collision occurred in extended workspace, and it was found be to a useful design tool which gives more flexibility to design conditions nd to find the mechanical constraints for fruit harvesting robots.

In this paper, we propose an algorithm of obstacle avoidance using fuzzy inferences. After the basic idea of the path generation algorithm using piecewise polynomials is described, the obstacle avoidance problem using fuzzy inferences is considered. Main concept of the avoidance algorithm is to modify intermittent point data using fuzzy inferences and to generate the collision free path based on the modified data. Finally, simulation result demonstrate the effectiveness of the proposed algorithm.

Ship's collision avoidance is a skill that masters of merchant marine vessels have acquired through years of experience and that makes them feel at ease to guide their ship out from danger quickly compared to inexperienced officers. Case based reasoning(CBR) uses the same technique in solving tasks that needs reference from variety of situations. CBR can render decision-making easier by retrieving past solutions from situations that are similar to the one at hand and make necessary adjustments in order to adapt them. In this paper, we propose to utilize the advantages of CBR in a support system for ship's collision avoidance while using fuzzy algorithm for its retrieval of similar navigational situations, stored in the casebase, thus avoiding the cumbersome tasks of creating a new solution each time a new situation is encountered. There will be two levels within the Fuzzy-CBR. The first level will identify the dangerous ships and index the new case. The second level will retrieve cases from casebase and adapt the solution to solve for the output. While CBR's accuracy depends on the efficient retrieval of possible solutions to be adapted from stored cases, fuzzy algorithm will improve the effectiveness of solving the similarity to a new case at hand.

A new collision avoidance algorithm is presented for two mobile robots in narrow corridor environments. When two robots meet each other in a narrow corridor, one should yield the way to the other robot. To solve the problem arising in this situation, they exchange their path to get information about crossing-points to check avoidance conditions, which are necessary for choosing the robot to yield. The conditions are summarized as follows. 1) If one robot blocks the path to the closest crossing-point in front of the other robot. 2) If the closest crossing-point of each robot is the same point. 3) Which robot is closer to the closest crossing-point. In this paper, we propose a path planning algorithm for the robot which yield the way. Simulation results are presented to verify the feasibility of the proposed collision avoidance algorithm.